Energy-Time Tradeoff in Recurrent Neural Nets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F15%3A00472477" target="_blank" >RIV/67985807:_____/15:00472477 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-09903-3_3" target="_blank" >http://dx.doi.org/10.1007/978-3-319-09903-3_3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-09903-3_3" target="_blank" >10.1007/978-3-319-09903-3_3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Energy-Time Tradeoff in Recurrent Neural Nets

Popis výsledku v původním jazyce

In this chapter, we deal with the energy complexity of perceptron networks which has been inspired by the fact that the activity of neurons in the brain is quite sparse (with only about 1% of neurons firing). This complexity measure has recently been introduced for feedforward architectures (i.e., threshold circuits). We shortly survey the tradeoff results which relate the energy to other complexity measures such as the size and depth of threshold circuits. We generalize the energy complexity for recurrent architectures which counts the number of simultaneously active neurons at any time instant of a computation. We present our energy-time tradeoff result for the recurrent neural nets which are known to be computationally as powerful as the finite automata. In particular, we show the main ideas of simulating any deterministic finite automaton by a low-energy optimal-size neural network. In addition, we present a lower bound on the energy of such a simulation (within a certain range of time overhead) which implies that the energy demands in a fixedsize network increase exponentially with the frequency of presenting the input bits.

Název v anglickém jazyce

Energy-Time Tradeoff in Recurrent Neural Nets

Popis výsledku anglicky

In this chapter, we deal with the energy complexity of perceptron networks which has been inspired by the fact that the activity of neurons in the brain is quite sparse (with only about 1% of neurons firing). This complexity measure has recently been introduced for feedforward architectures (i.e., threshold circuits). We shortly survey the tradeoff results which relate the energy to other complexity measures such as the size and depth of threshold circuits. We generalize the energy complexity for recurrent architectures which counts the number of simultaneously active neurons at any time instant of a computation. We present our energy-time tradeoff result for the recurrent neural nets which are known to be computationally as powerful as the finite automata. In particular, we show the main ideas of simulating any deterministic finite automaton by a low-energy optimal-size neural network. In addition, we present a lower bound on the energy of such a simulation (within a certain range of time overhead) which implies that the energy demands in a fixedsize network increase exponentially with the frequency of presenting the input bits.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/GBP202%2F12%2FG061" target="_blank" >GBP202/12/G061: Centrum excelence - Institut teoretické informatiky (CE-ITI)</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Artificial Neural Networks. Methods and Applications in Bio-/Neuroinformatics

ISBN

978-3-319-09902-6

ISSN

2193-9349

e-ISSN

—

Počet stran výsledku

12

Strana od-do

51-62

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Sofia

Datum konání akce

10. 9. 2013

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000380528700003